© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5933
    Prev
    Next
    INDEX
    Explanations

    polar, polarization, polar ice, polar bears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sàng
    1.95
     kickoff
    1.88
    ست
    1.80
    いる
    1.78
     kilka
    1.76
    ¿
    1.73
    いた
    1.72
    いますが
    1.70
    る
    1.70
    indest
    1.69
    POSITIVE LOGITS
     établ
    2.41
    ار
    2.19
     striées
    2.06
    cion
    2.00
    selves
    1.99
     offrent
    1.99
    ა
    1.99
     variés
    1.95
     défin
    1.93
    이면
    1.93
    Activations Density 0.021%

    No Known Activations